郭 交，劉 健，寧紀(jì)鋒，韓文霆

基于Sentinel多源數(shù)據(jù)的農(nóng)田地表土壤水分反演模型構(gòu)建與驗(yàn)證

郭 交1,2，劉 健1,2，寧紀(jì)鋒3，韓文霆4

（1.西北農(nóng)林科技大學(xué)機(jī)械與電子工程學(xué)院，楊凌 712100；2. 陜西省農(nóng)業(yè)信息感知與智能服務(wù)重點(diǎn)實(shí)驗(yàn)室，楊凌 712100；3. 西北農(nóng)林科技大學(xué)信息工程學(xué)院，楊凌 712100；4. 西北農(nóng)林科技大學(xué)水土保持研究所，楊凌 712100）

土壤水分是影響水文、生態(tài)和氣候等環(huán)境過程的重要參數(shù)，而微波遙感是農(nóng)田地表土壤水分測量的重要手段之一。針對微波遙感反演農(nóng)田地表土壤水分受植被覆蓋影響較大的問題，該文基于Sentinel-1和Sentinel-2多源遙感數(shù)據(jù)，利用Oh模型、支持向量回歸（support vector regression，SVR）和廣義神經(jīng)網(wǎng)絡(luò)（generalized regression neural Network，GRNN）模型對土壤水分進(jìn)行定量反演，以減小植被影響，提高反演精度。結(jié)果表明：通過水云模型去除植被影響后的Oh模型反演精度有所提高。加入不同植被指數(shù)的SVR和GRNN模型的反演效果總體優(yōu)于Oh模型，基于SVR模型的多特征參數(shù)組合（雙極化雷達(dá)后向散射系數(shù)、海拔高度、局部入射角、修改型土壤調(diào)整植被指數(shù)）反演效果最優(yōu)，其測試集相關(guān)系數(shù)和均方根誤差分別達(dá)到了0.903和0.015 cm3/cm3，為利用多源遙感數(shù)據(jù)反演農(nóng)田地表土壤水分提供了參考。

土壤水分；模型；遙感；反演；多源數(shù)據(jù)；Sentinel

0 引 言

土壤水分是地球生態(tài)系統(tǒng)中非常重要的組成部分，在全球水循環(huán)中發(fā)揮著積極作用[1]，其直接影響著地表和大氣界面的水分和能量交換，在全球氣候變化和水循環(huán)的研究中扮演著重要的角色[2-3]。在農(nóng)業(yè)應(yīng)用中，土壤水分監(jiān)測在農(nóng)作物長勢監(jiān)測、作物估產(chǎn)和變量灌溉等應(yīng)用中具有重要意義[4-5]。

在現(xiàn)有土壤水分監(jiān)測方法中，合成孔徑雷達(dá)（synthetic aperture radar，SAR）遙感是一種常用方式，其具有全天時(shí)、全天候工作的優(yōu)勢，適合定量反演農(nóng)田地表土壤水分。為了反演土壤水分，需要建立雷達(dá)后向散射系數(shù)與介電常數(shù)之間的關(guān)系，而土壤的介電常數(shù)與土壤水分之間存在密切的聯(lián)系[6-9]。何連等[10]利用多時(shí)相Sentinel-1雷達(dá)數(shù)據(jù)，實(shí)現(xiàn)了農(nóng)田地表土壤水分的反演，驗(yàn)證結(jié)果表明土壤水分反演結(jié)果精度較好。尹楠等[11]基于RADARSAT-2全極化數(shù)據(jù)，通過修正Oh模型對研究區(qū)的土壤水分進(jìn)行反演，驗(yàn)證表明預(yù)測結(jié)果較好。雖然利用雷達(dá)數(shù)據(jù)可以有效地反演裸土水分，但農(nóng)田中土壤表層常有植被覆蓋，所以在實(shí)際中單純利用雷達(dá)數(shù)據(jù)有著極大的局限性。為克服這一缺點(diǎn)，張鈞泳等[12]以Sentinel-1雷達(dá)數(shù)據(jù)和Landsat-8光學(xué)數(shù)據(jù)為數(shù)據(jù)源，利用水云模型去除植被影響后反演了土壤表層水分以及地下水埋深；蔡慶空等[13]利用RADARSAT-2雷達(dá)數(shù)據(jù)和Landsat-8光學(xué)數(shù)據(jù)基于水云模型去除植被影響后反演了農(nóng)田土壤水分，為大面積反演土壤水分提供了研究思路。

雖然理論上利用水云模型可去除植被影響，但對不同植被類型，該模型參數(shù)需重新計(jì)算，模型的普適性不足。所以有學(xué)者直接通過植被指數(shù)來考慮植被覆蓋影響，如Holtgrave等[14]利用Landsat-8數(shù)據(jù)計(jì)算歸一化植被指數(shù)NDVI補(bǔ)償植被對SAR的反向散射影響，基于SVR模型反演洪澇區(qū)的土壤水分，取得了較好的結(jié)果。雖然NDVI可以有效減小植被覆蓋影響，但缺乏與其它植被指數(shù)的對比分析。另外，Landsat-8衛(wèi)星的空間分辨率為30 m，重訪周期為16天[15]，其分辨率和重訪周期無法滿足及時(shí)準(zhǔn)確的監(jiān)測需求。而Sentinel-2的空間分辨率為10 m，重訪周期為5天，且Sentinel-1與Sentinel-2同屬于歐空局的Sentinel系列衛(wèi)星（以下簡稱S1、S2），在空間、時(shí)間和數(shù)據(jù)配準(zhǔn)方面，更適合監(jiān)測土壤水分。

本文基于S1和S2多源遙感數(shù)據(jù)，以陜西省楊凌示范區(qū)周邊農(nóng)田區(qū)域?yàn)檠芯繀^(qū)，針對Oh模型利用S1雷達(dá)數(shù)據(jù)反演土壤水分受植被覆蓋影響較大的問題，通過S2光學(xué)遙感數(shù)據(jù)計(jì)算植被指數(shù)，分別利用傳統(tǒng)的水云模型、SVR和GRNN模型減小植被覆蓋對土壤水分反演精度的影響，并在此基礎(chǔ)上分析了不同特征參數(shù)組合下SVR和GRNN模型反演土壤水分的精度，為應(yīng)用雷達(dá)和光學(xué)多源數(shù)據(jù)反演土壤水分提供研究思路，本文具體技術(shù)路線如圖1所示。

圖1 技術(shù)路線圖

1 研究區(qū)與數(shù)據(jù)源

1.1 研究區(qū)概況

研究區(qū)為陜西省楊凌示范區(qū)周邊，該區(qū)域土壤肥沃，位于107°55′20″E－108°15′40″E，34°15′15″N－34°50′28″N，地勢相對比較平坦，北部較南部略高，海拔高度介于560～790 m之間，屬于東亞暖溫帶半濕潤半干旱氣候，具有春暖多風(fēng)，夏熱多雨、冬寒干燥等明顯的大陸性季風(fēng)氣候特征，年均氣溫約12 ℃，無霜期211天，年均日照時(shí)數(shù)約2163 h，年均降水量635 mm。研究區(qū)主要作物為冬小麥，數(shù)據(jù)采集時(shí)小麥處于生長初期。

研究區(qū)面積為20 km×20 km，地面數(shù)據(jù)采集時(shí)間為2018年3月12日，S1衛(wèi)星當(dāng)天從研究區(qū)過境，S2衛(wèi)星于2018年3月10日過境，以保證實(shí)測時(shí)間與衛(wèi)星過境時(shí)間盡量一致。在研究區(qū)選取45個(gè)點(diǎn)作為采樣點(diǎn)，實(shí)地采集土壤水分值、土壤粗糙度、經(jīng)緯度坐標(biāo)等地面參數(shù)，采樣點(diǎn)分布如圖2a所示。土壤水分利用TDR300型土壤水分計(jì)進(jìn)行測量，測量時(shí)采用的探針長度為7.5 cm，用于獲取表層土壤的體積含水量。在以采樣點(diǎn)為中心半徑5 m的范圍內(nèi)布置5個(gè)測量點(diǎn)，測量點(diǎn)呈“+”字形分布，每個(gè)測量點(diǎn)測5次。每個(gè)采樣點(diǎn)的土壤水分是5個(gè)測量點(diǎn)的平均值。土壤粗糙度采用針式粗糙度儀進(jìn)行測量，剖面板長度為1 m，相鄰探針間隔1 cm，測量時(shí)沿同一方向連續(xù)測量5次，構(gòu)成5 m的剖面用于求取粗糙度。采樣點(diǎn)的經(jīng)緯度坐標(biāo)通過雙頻GPS（global positioning system）接收機(jī)進(jìn)行定位測量，測量精度為厘米級，遠(yuǎn)小于遙感影像分辨率。

1.2 數(shù)據(jù)源及預(yù)處理

圖2 遙感影像及采樣點(diǎn)分布

2 研究方法

2.1 Oh模型分析

式中為入射角，rad；m為土壤體積含水量，cm3/cm3；為均方根高度，cm；為自由空間波數(shù)（=2p/，為頻率，為波速），cm-1。盡管理論上Oh模型的適用范圍較寬，但實(shí)際上，對粗糙或干燥的土壤，Oh模型的適用性并不好[11]。

對本文研究區(qū)地表參數(shù)的實(shí)測數(shù)據(jù)分析發(fā)現(xiàn)，土壤體積含水量實(shí)測值分布在0.081～0.284 cm3/cm3，平均值為0.182 cm3/cm3；均方根高度的實(shí)測值為0.452～1.453 cm，平均值為0.862 cm，均處于模型適用范圍。因此，Oh模型適用于本研究區(qū)。

2.2 水云模型分析

Oh模型適用于反演裸土水分，但在實(shí)際應(yīng)用中，通過雷達(dá)圖像提取的后向散射系數(shù)中包含土壤表層植被的影響，直接利用Oh模型反演精度較低，故有學(xué)者通過水云模型分離植被的后向散射系數(shù)，以提高反演精度[20-22]。水云模型如式（4）－（6）所示

本研究區(qū)的植被類型主要為冬小麥，根據(jù)文獻(xiàn)[23]，式（5）、（6）中和分別取0.0018和0.138。植被含水量VWC是水云模型的重要輸入?yún)?shù)，本文利用與S1過境時(shí)間相近的S2光學(xué)數(shù)據(jù)來計(jì)算NDVI。根據(jù)NDVI和VWC的關(guān)系[24-25]，VWC可表示如下：

2.3 SVR模型分析

SVR就是支持向量機(jī)（support vector machine，SVM）在函數(shù)擬合上的應(yīng)用，其基于VC維的統(tǒng)計(jì)理論和最小化結(jié)構(gòu)風(fēng)險(xiǎn)理論，可以利用有限的樣本數(shù)量選擇合適的核函數(shù)實(shí)現(xiàn)高維空間的線性回歸，根據(jù)泛函數(shù)的相關(guān)理論，當(dāng)核函數(shù)(x,)滿足Mercer定理時(shí)，對應(yīng)的預(yù)測函數(shù)為[26]。

在本文的土壤水分反演中，利用SVR構(gòu)建模型主要步驟如下：（1）構(gòu)建數(shù)據(jù)集，輸入特征參數(shù)包括雙極化雷達(dá)后向散射系數(shù)、海拔高度和局部入射角以及3種植被指數(shù)（NDVI、MSAVI、DVI）；（2）劃分訓(xùn)練集和測試集，本文選擇36個(gè)樣本作為模型的訓(xùn)練集，9個(gè)樣本作為模型的測試集；（3）SVR模型的核函數(shù)選擇高斯徑向基函數(shù)，通過網(wǎng)格參數(shù)尋優(yōu)法確定懲罰因子和參數(shù)；（4）模型預(yù)測效果通過測試集的均方根誤差和相關(guān)系數(shù)來評價(jià)。

2.4 GRNN模型分析

廣義神經(jīng)網(wǎng)絡(luò)（GRNN）是一種以徑向基函數(shù)為核函數(shù)的一種局部逼近網(wǎng)絡(luò)，研究表明該網(wǎng)絡(luò)對小樣本預(yù)測有一定優(yōu)勢[27]。該網(wǎng)絡(luò)由輸入層、模式層、求和層和輸出層構(gòu)成，網(wǎng)絡(luò)輸入為各特征參數(shù)，網(wǎng)絡(luò)輸出為土壤水分預(yù)測值。GRNN的基本原理是非線性回歸分析[28]，其預(yù)測函數(shù)可表示為：

式中為訓(xùn)練樣本數(shù)，為光滑因子，()是所有樣本觀測值的加權(quán)平均值，每個(gè)觀測值y的權(quán)重因子通過對應(yīng)樣本x和網(wǎng)絡(luò)輸入的歐氏距離平方確定。在土壤水分反演過程中，GRNN構(gòu)建模型時(shí)通過交叉驗(yàn)證法確定光滑因子，其它步驟和SVR模型構(gòu)建過程相同。

3 結(jié)果與分析

3.1 Oh模型反演結(jié)果分析

利用水云模型去除植被影響前后Oh模型的反演結(jié)果驗(yàn)證如圖3所示。從圖3a和3b中可以看出，去除植被影響前測試集相關(guān)系數(shù)R和均方根誤差RMSE分別為0.628和0.028 cm3/cm3，利用水云模型去除植被影響后測試集2和RMSE分別為0.650和0.025 cm3/cm3。利用水云模型去除植被影響后，2提高了0.022，RMSE減小了0.003 cm3/cm3，可知去除植被影響后反演的效果更好。

圖3 去除植被影響前后Oh模型反演結(jié)果驗(yàn)證

3.2 SVR反演結(jié)果分析

對比4a、4d、4g，4b、4e、4h，4c、4f、4i這3組結(jié)果可以看出，基于3種植被指數(shù)NDVI、MSAVI和DVI的反演結(jié)果中MSAVI和NDVI的2均大于DVI，RMSE均小于DVI。由此可知，SVR模型反演土壤水分時(shí)，3種植被指數(shù)中DVI與土壤水分的相關(guān)性最弱。

圖4 基于不同特征參數(shù)組合的SVR模型土壤水分反演結(jié)果驗(yàn)證

3.3 GRNN反演結(jié)果分析

對比5a、5d、5g，5b、5e、5h，5c、5f、5i這3組結(jié)果可以看出，基于3種植被指數(shù)NDVI、MSAVI和DVI的反演結(jié)果中MSAVI和NDVI的2均大于DVI，RMSE均小于DVI。由此可知，GRNN模型反演土壤水分時(shí)，3種植被指數(shù)中DVI與土壤水分的相關(guān)性最弱。

圖5 基于不同特征參數(shù)組合的GRNN模型土壤水分反演結(jié)果驗(yàn)證

利用前文所構(gòu)建的SVR最優(yōu)模型和3個(gè)時(shí)相的數(shù)據(jù)對整個(gè)試驗(yàn)區(qū)進(jìn)行土壤水分反演，結(jié)果如圖6所示。2月28日土壤水分反演結(jié)果整體較高，試驗(yàn)區(qū)土壤水分均值為0.307 cm3/cm3，這是由于在衛(wèi)星過境前兩日試驗(yàn)區(qū)有持續(xù)降雨，所以土壤比較濕潤。3月12日反演的試驗(yàn)區(qū)土壤水分均值為0.245 cm3/cm3，衛(wèi)星過境前試驗(yàn)區(qū)域僅有少量降雨，故土壤水分值相比于2月28日略有降低。3月24日反演的土壤水分值最低，均值為0.186 cm3/cm3，這是因?yàn)榍耙恢芴鞖馇缋薀o降雨過程。由此可知，3個(gè)時(shí)間的土壤水分反演結(jié)果與降雨情況比較吻合，該模型在試驗(yàn)區(qū)具有較強(qiáng)的適用性。

3.4 特征參數(shù)重要性分析

圖6 試驗(yàn)區(qū)不同時(shí)期地表土壤水分反演結(jié)果

圖7 特征參數(shù)等效出現(xiàn)次數(shù)

4 結(jié) 論

本文利用S1和S2多源遙感數(shù)據(jù)作為數(shù)據(jù)源進(jìn)行土壤水分定量反演，通過水云模型去除植被影響，利用Oh模型、SVR和GRNN模型反演土壤水分，探討了雷達(dá)后向散射系數(shù)、海拔高度、局部入射角、3種植被指數(shù)等參數(shù)對土壤水分反演精度的影響，主要結(jié)論包括：

1）對于Oh模型而言，通過水云模型去除植被影響后其反演效果更好；對于SVR和GRNN模型而言，植被指數(shù)為MSAVI和NDVI時(shí)反演效果優(yōu)于Oh模型?；赟VR模型的最佳組合測試集2和RMSE分別為0.903和0.015 cm3/cm3，相比于GRNN最優(yōu)組合，SVR最優(yōu)組合的2提高了0.026，RMSE減小了0.008 cm3/cm3，相比于去除植被影響后Oh模型的反演結(jié)果，SVR最優(yōu)組合的2提高了0.253，RMSE減小了0.010 cm3/cm3。

2）通過分析各特征參數(shù)對土壤水分反演結(jié)果的影響，驗(yàn)證了雷達(dá)后向散射系數(shù)、海拔高度、局部入射角、植被指數(shù)對農(nóng)田地表土壤水分反演的重要影響，同時(shí)發(fā)現(xiàn)3種植被指數(shù)對土壤水分的相關(guān)性由大到小為：MSAVI、NDVI、DVI。

本研究區(qū)的植被類型主要為冬小麥，后續(xù)的研究中將進(jìn)一步探討模型在其它農(nóng)田地表類型的適用性。S1雷達(dá)與S2光學(xué)衛(wèi)星同屬歐空局的Sentinel系列衛(wèi)星，在多源影像配準(zhǔn)和融合方面具有較大優(yōu)勢，在農(nóng)田土壤水分反演等應(yīng)用中具有巨大潛力。

[1] Anagnostopoulos V, Petropoulos G P, Ireland G, et al. A modernized version of a 1D soil vegetation atmosphere transfer model for improving its future use in land surface interactions studies[J]. Environmental Modelling and Software, 2017, 90: 147－156.

[2] Leng Pei, Song Xiaoning, Duan Sibo, et al. A practical algorithm for estimating surface soil moisture using combined optical and thermal infrared data[J]. International Journal of Applied Earth Observation and Geoinformation, 2016, 52: 338－348.

[3] Rahimzadeh-Bajgiran P, Berg A A, Champagne C, et al. Estimation of soil moisture using optical/thermal infrared remote sensing in the Canadian Prairies[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 83(3): 94－103.

[4] Wang Hongquan, Magagi R, Goita K. Potential of a two-component polarimetric decomposition at C-band for soil moisture retrieval over agricultural fields[J]. Remote Sensing of Environment, 2018, 217: 38－51.

[5] Stamenkovic J, Guerriero L, Ferrazzoli P, et al. Soil moisture estimation by SAR in alpine fields using Gaussian Process Regressor trained by model simulations[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(9): 4899－4912.

[6] Nelson D G A, Shariati M, Glena R, et al. Application of the Dubois-model using experimental synthetic aperture radar data for the determination of soil moisture and surface roughness[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 1999, 54(4): 273－278.

[7] Hosseini M, Mcnairn H. Using multi-polarization C- and L-band synthetic aperture radar to estimate biomass and soil moisture of wheat fields[J]. International Journal of Applied Earth Observation and Geoinformation, 2017, 58: 50－64.

[8] Xu Xiaoyong, Tolson B A, Li J, et al. Comparison of X-band and L-Band soil moisture retrievals for land data assimilation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(9): 3850－3860.

[9] Pasolli L, Notarnicola C, Bruzzone L. Estimating soil moisture with the Support Vector Regression technique[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8(6): 1080－1084.

[10] 何連，秦其明，任華忠，等. 利用多時(shí)相Sentinel-1 SAR數(shù)據(jù)反演農(nóng)田地表土壤水分[J]. 農(nóng)業(yè)工程學(xué)報(bào)，2016，32(3)：142－148.

He Lian, Qin Qiming, Ren Huazhong, et al. Soil moisture retrieval using multi-temporal Sentinel-1 SAR data in agricultural areas[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2016, 32(3): 142－148. (in Chinese with English abstract)

[11] 尹楠，姜琦剛，孟治國，等. 基于RADARSAT-2全極化數(shù)據(jù)反演周期性地表土壤濕度[J]. 農(nóng)業(yè)工程學(xué)報(bào)，2013，29(17)：72－79.

Yin Nan, Jiang Qigang, Meng Zhiguo, et al. Use of fully polarimetric RADARSAT-2 data to retrieve soil moisture of periodic surfaces[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2013, 29(17): 72－79. (in Chinese with English abstract)

[12] 張鈞泳，丁建麗，譚嬌. 基于SVM 的綠洲荒漠交錯(cuò)帶土壤水分與淺層地下水埋深反演[J]. 農(nóng)業(yè)機(jī)械學(xué)報(bào)，2019，50(3)：221－230.

Zhang Junyong, Ding Jianli, Tan Jiao. Quatitative estimation of soil moisture and shallow groundwater level using SVM in arid oasis-desert[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(3): 221－230. (in Chinese with English abstract)

[13] 蔡慶空，李二俊，陶亮亮，等. PROSAIL 模型和水云模型耦合反演農(nóng)田土壤水分[J]. 農(nóng)業(yè)工程學(xué)報(bào)，2018，34(20)：117－123.

Cai Qingkong, Li Erjun, Tao Liangliang, et al. Farmland soil moisture retrieval using PROSAIL and water cloud model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(20): 117－123. (in Chinese with English abstract)

[14] Holtgrave A K, Foerster M, Greifeneder F, et al. Estimation of soil moisture in vegetation-covered floodplains with Sentinel-1 SAR data using Support Vector Regression[J]. PFG-Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 2018, 86(2): 85－101.

[15] Bao Yansong, Lin Libin, Wu Shanyu, et al. Surface soil moisture retrievals over partially vegetated areas from the synergy of Sentinel-1 and Landsat 8 data using a modified water-cloud model[J]. International Journal of Applied Earth Observation and Geoinformation, 2018, 72: 76－85.

[16] Lee J S, Grunes M R, Grandi G De. Polarimetric SAR speckle filtering and its implication for classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(5): 2363－2373

[17] Oh Y, Sarabandi K, Ulaby F T. An empirical model and an inversion technique for radar scattering from bare soil surface[J]. IEEE Transaction on Geoscience and Remote Sensing, 1992, 30(2): 370－381.

[18] Oh Y, Sarabandi K, Ulaby F T. Semi-empirical model of the ensemble averaged differential Mueller matrix for microwave backscattering from bare soil surfaces[J]. IEEE Transactions on Geoscience and Remote Sensing, 2002, 40(6): 1348－1355.

[19] Oh Y. Quantitative retrieval of soil moisture content and surface roughness from multipolarized radar observations of bare soil surfaces[J]. IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(3): 596－601.

[20] Emilie B, FranOis W, FranOis C, et al. Maize leaf area index retrieval from synthetic quad Pol SAR time series using the water cloud model[J]. Remote Sensing, 2015, 7(12): 16204－16225.

[21] Kumar K, Suryanarayana Rao H P, Arora M K. Study of water cloud model vegetation descriptors in estimating soil moisture in Solani catchment[J]. Hydrological Processes, 2015, 29(9): 2137－2148.

[22] Liu Chenzhou, Shi Jiancheng. Estimation of vegetation parameters of water cloud model for global soil moisture retrieval using time-series L-band aquarius observations[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(12): 5621－5633.

[23] Bindlish R, Barros A P. Parameterization of vegetation backscatter in radar-based, soil moisture estimation[J]. Remote Sensing of Environment, 2001, 76(1): 130－137.

[24] Jackson T J, Vine D M L, Hsu A Y, et al. Soil moisture mapping at regional scales using microwave radiometry: the Southern Great Plains Hydrology Experiment[J]. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(5): 2136－2151.

[25] Kong Jinling, Yang Jing, Zhen Peipei, et al. A coupling model for soil moisture retrieval in sparse vegetation covered areas based on microwave and optical remote sensing data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(12): 7162－7173.

[26] Brereton R G, Lloyd G R. Support Vector Machines for classification and regression[J]. Analyst, 2010, 135(2): 230－267.

[27] Li Weide, Yang Xuan, Li Hao, et al. Hybrid forecasting approach based on GRNN neural network and SVR machine for electricity demand forecasting[J]. Energies, 2017, 10: 44.

[28] Naguib R N G, Hamdy F C. A general regression neural network analysis of prognostic markers in prostate cancer[J]. Neurocomputing, 1998, 19: 145－150.

Construction and validation of soil moisture retrieval model in farmland based on Sentinel multi-source data

Guo Jiao1,2, Liu Jian1,2, Ning Jifeng3, Han Wenting4

(1.712100; 2.712100,;3.712100,4.712100,)

As an important component of the earth ecosystem, soil moisture is of great significance in the fields of crop growth monitoring, crop yield estimation, variable irrigation and other related agricultural applications. With the rapid development of the technology and theory of microwave remote sensing, soil moisture retrieval with remote sensing data has been widely used at home and abroad.The multi-source remote sensing data used in this study was acquired from Sentinel-1 radar and Sentinel-2 optical satellites which belong to ESA's Sentinel series and there are great advantages in space, time and data registration in monitoring soil moisture. The study area is located in Yangling Demonstration Zone, Shanxi Province and 45 sampling sites were selected and measured to validate the soil moisture retrieval model. Firstly, to deal with the problem that soil moisture retrieval was greatly affected by surface vegetation covers, this study applied Oh model to retrieve soil moisture after removing the influence of vegetation by water cloud model. Secondly, taking the great advantages of machine learning algorithms into account, the study selected support vector regression (SVR) and generalized regression neural network (GRNN) models to retrieve soil moisture, and the models were constructed with different combinations of characteristic parameters including VH polarization radar backward scattering coefficient and VV polarization radar backward scattering coefficient altitude (0), local incident angle (LIA) which were calculated out with Sentinel-1 radar remote sensing data and vegetation indexes (normalized difference vegetation index, NDVI; modified soil adjusted vegetation index, MSAVI and difference vegetation index, DVI) which were calculated out with Sentinel-2 optical remote sensing data. Finally, this study defined the equivalent number of occurrences to evaluate the quantitative influence of each characteristic parameter because different parameters had different effect on farmland soil moisture retrieval. The results showed that the soil moisture retrieval accuracy of Oh model was increased after removing vegetation influence by water cloud model. The retrieval accuracies of SVR and GRNN models with MSAVI and NDVI were higher than that of Oh model. The optimal input combination of SVR model composed of five characteristic parameters, including VH polarization radar backward scattering coefficient, VV polarization radar backward scattering coefficient,0, LIA, and MSAVI had the best retrieval accuracy with correlation coefficient of 0.903 and root mean square error of 0.014cm3/cm3respectively. The optimal SVR model was used to retrieve the soil moisture in study area and the results were consistent with local rainfall events. The equivalent numbers of occurrences of characteristic parameters from high to low were VH polarization radar backward scattering coefficient,0, VV polarization radar backward scattering coefficient, LIA, MSAVI, NDVI, DVI. For radar backward scattering coefficients from different polarized channel, VH polarization radar backward scattering coefficient is more sensitive to soil moisture than VV polarization radar backward scattering coefficient. Among the three vegetation indexes, the counting results indicated MSAVI had the strongest correlation with soil moisture content, followed by NDVI and DVI was the weakest. The experimental results showed that the fusion of radar and optical data had great potential in soil moisture retrieval in farmlands. The performances of the constructed model in other farmland types would be further investigated in the future.

soil moisture; models; remote sensing; retrieval; multi-source data; Sentinel

2019-01-23

2019-06-30

國家自然科學(xué)基金資助項(xiàng)目（41301450）、“十三五”國家重點(diǎn)研發(fā)計(jì)劃課題（2017YFC0403203）、楊凌示范區(qū)產(chǎn)學(xué)研用協(xié)同創(chuàng)新重大項(xiàng)目（2018CXY-23）和中央高?；究蒲袠I(yè)務(wù)費(fèi)專項(xiàng)資金資助項(xiàng)目（2452019180）

郭 交，副教授，博士，研究方向?yàn)檗r(nóng)業(yè)遙感和精準(zhǔn)農(nóng)業(yè)。Email：jiao.g@163.com

10.11975/j.issn.1002-6819.2019.14.009

S24

A

1002-6819(2019)-14-0071-08

郭 交，劉 健，寧紀(jì)鋒，韓文霆. 基于Sentinel多源數(shù)據(jù)的農(nóng)田地表土壤水分反演模型構(gòu)建與驗(yàn)證[J]. 農(nóng)業(yè)工程學(xué)報(bào)，2019，35(14)：71－78. doi：10.11975/j.issn.1002-6819.2019.14.009 http://www.tcsae.org

Guo Jiao, Liu Jian, Ning Jifeng, Han Wenting. Construction and validation of soil moisture retrieval model in farmland based on Sentinel multi-source data[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2019, 35(14): 71－78. (in Chinese with English abstract) doi：10.11975/j.issn.1002-6819.2019.14.009 http://www.tcsae.org